commit 4aa2933f2c4432654e56b0110303183008011229 Author: ModelHub XC Date: Fri Jun 12 11:15:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/airoboros-7b-gpt4-1.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c32451 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.f16.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-7b-gpt4-1.4.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4edfcae --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: jondurbin/airoboros-7b-gpt4-1.4 +datasets: +- jondurbin/airoboros-gpt4-1.4 +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-7b-gpt4-1.4-GGUF/resolve/main/airoboros-7b-gpt4-1.4.f16.gguf) | f16 | 13.6 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/airoboros-7b-gpt4-1.4.IQ4_XS.gguf b/airoboros-7b-gpt4-1.4.IQ4_XS.gguf new file mode 100644 index 0000000..51d4f8d --- /dev/null +++ b/airoboros-7b-gpt4-1.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:681836f2420fbf22e5ae214d6c765653b295d59ddebf6598848cf391b64b8250 +size 3647517440 diff --git a/airoboros-7b-gpt4-1.4.Q2_K.gguf b/airoboros-7b-gpt4-1.4.Q2_K.gguf new file mode 100644 index 0000000..bbac61c --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b5247ff43301f027d4bec944841d6a8ee12c01f56a03fdf9e70b345fe33519 +size 2532864768 diff --git a/airoboros-7b-gpt4-1.4.Q3_K_L.gguf b/airoboros-7b-gpt4-1.4.Q3_K_L.gguf new file mode 100644 index 0000000..ada8e2a --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1000331a93fc64498ab0780d22bfb6daec1a32aaacc742e935566406a847d962 +size 3597112064 diff --git a/airoboros-7b-gpt4-1.4.Q3_K_M.gguf b/airoboros-7b-gpt4-1.4.Q3_K_M.gguf new file mode 100644 index 0000000..4ee71b2 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f1cc540a13a1dfe9dba418ac59fc6808a864b8884f17fa557d63193a1fa1fa +size 3298005760 diff --git a/airoboros-7b-gpt4-1.4.Q3_K_S.gguf b/airoboros-7b-gpt4-1.4.Q3_K_S.gguf new file mode 100644 index 0000000..ea5fbfe --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a11ec9533d2ae55267170d6fb5be65b0431cdb8ac2ff80cb575c66cb5224b53 +size 2948305664 diff --git a/airoboros-7b-gpt4-1.4.Q4_0_4_4.gguf b/airoboros-7b-gpt4-1.4.Q4_0_4_4.gguf new file mode 100644 index 0000000..f163abe --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c80140f90a9a3e6115a11dc523c418b85f2f4bb9cf0e8e643acc72f68a44f57 +size 3825808128 diff --git a/airoboros-7b-gpt4-1.4.Q4_K_M.gguf b/airoboros-7b-gpt4-1.4.Q4_K_M.gguf new file mode 100644 index 0000000..3b43cd7 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be9c650f558def2e3c3ab73fb2cf8b85a6a145cfaea9c01ade20e9661891b0b +size 4081005312 diff --git a/airoboros-7b-gpt4-1.4.Q4_K_S.gguf b/airoboros-7b-gpt4-1.4.Q4_K_S.gguf new file mode 100644 index 0000000..00e6b9d --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b6e785f306b58f36a49b9d08fd304d3470c52468ca50e35e27c9f3b284c6e9 +size 3856741120 diff --git a/airoboros-7b-gpt4-1.4.Q5_K_M.gguf b/airoboros-7b-gpt4-1.4.Q5_K_M.gguf new file mode 100644 index 0000000..5d524fc --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085e4b2f8c9e18f35b7fdc2458b70c7276a3391947ab8f60d90a6e0507677c96 +size 4783158016 diff --git a/airoboros-7b-gpt4-1.4.Q5_K_S.gguf b/airoboros-7b-gpt4-1.4.Q5_K_S.gguf new file mode 100644 index 0000000..9701520 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8def092c16c9cb42e9a89977350b666169814298ef2128b788f5347a8a4748ff +size 4651692800 diff --git a/airoboros-7b-gpt4-1.4.Q6_K.gguf b/airoboros-7b-gpt4-1.4.Q6_K.gguf new file mode 100644 index 0000000..e0b9101 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed165e27b361a78ff7649b7a257215557831609ff7e3e3fa9b64b60c23e7210f +size 5529195264 diff --git a/airoboros-7b-gpt4-1.4.Q8_0.gguf b/airoboros-7b-gpt4-1.4.Q8_0.gguf new file mode 100644 index 0000000..5199f62 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3674cf75b6bc4b1c2e7f9041351ec6b64745c1d88e34a728884308625583b20 +size 7161090816 diff --git a/airoboros-7b-gpt4-1.4.f16.gguf b/airoboros-7b-gpt4-1.4.f16.gguf new file mode 100644 index 0000000..c1d5db1 --- /dev/null +++ b/airoboros-7b-gpt4-1.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34544ec58a413e06edc296ee0bd714e05148d80cc85898b04e7c093efec911be +size 13478105856